Skip to main navigation menu Skip to main content Skip to site footer

InnovFaceNet: Deep Face Recognition for Industrial Environments

Abstract

In recent times the usage of intelligent systems have paved way for
many applications to be robust and self-reliant. One such popular
and vast growing technology is face recognition. Facial Recognition
technology is used in security, surveillance, criminal justice systems
and many other multimedia platforms. This work proposes a real
time facial recognition technology which can be used in any industrial
setup eliminating manual supervision, ensuring authorized access
to the personnel in the plant. Due to the recent development of
COVID-19 pandemic around the world, wearing masks has become
a necessity. Our proposed facial recognition technology identifies a
person’s face with mask or no mask in real time with a speed of
20 FPS on a CPU and an F1-score of 95.07%. This makes our
algorithm fast, secure, robust and deployable on a simple personal
computer or any edge device at any industrial plant or organization.

PDF